Static information storage and retrieval – Addressing – Sync/clocking
Reexamination Certificate
2001-01-03
2001-09-25
Verbrugge, Kevin (Department: 2185)
Static information storage and retrieval
Addressing
Sync/clocking
C711S104000, C711S167000, C713S600000
Reexamination Certificate
active
06295246
ABSTRACT:
BACKGROUND
1. Field of the Invention
The present invention relates to memory systems for computers, and more particularly to the design of a memory interface that receives data and a clock signal from a memory during a read operation.
2. Related Art
As processor speed continually increase, memory systems are under increasing pressure to provide data at faster rates. This has recently led to the development of new memory system designs. Memory latencies have been dramatically decreased by using page mode and extended data out (EDO) memory designs, which achieve a high burst rate and low latencies within a single page of memory. Another recent innovation is to incorporate a synchronous clocked interface into a memory chip, thereby allowing data from within the same page of memory to be clocked out of the memory in a continuous stream. Such memory chips, with clocked interfaces are known as synchronous random access memories.
Recently, standards such as Rambus and SyncLink have been developed to govern the transfer of data between memory and processor using such clocked interfaces. SyncLink, which will be known as IEEE Standard 1596.7, specifies an architecture that supports a 64 M-bit memory with a data transfer rate of 1.6 gigabytes per second. SyncLink packetizes and pipelines the address, command and timing signals, and adds features that significantly increase data bus speed, thereby providing fast memory accesses without losing the ability to move quickly from row to row or to obtain bursts of data.
During read operations, synchronous random access memories return a data clock signal along with the data; this data clock signal is used to clock the data into the processor (or into a memory controller attached to the processor). This feature is a significant difference from conventional memory systems, which rely on the system clock to receive data during read operations.
Designing an interface that receives a high-speed data clock from a synchronous random access memory during a read operation presents challenges because at some point data returned during a read operation must be transferred from the high speed data clock domain into the slower speed system clock domain. This is hard to accomplish because the slower speed circuitry must somehow be able to match the data transfer rate of the high-speed circuitry. Additionally, the slower speed circuitry typically requires more setup and hold time for memory elements than is provided by the high-speed circuitry.
What is needed is a system that receives data along with an associated high-speed clock from a memory during a read operation, and that transfers this data into circuitry that is clocked by a slower system clock.
SUMMARY
One embodiment of the present invention provides a method for receiving data from a synchronous random access memory. This method receives a stream of data along with a data clock signal from the synchronous random access memory. This stream of data is alternately clocked into a first memory register and a second memory register using the data clock signal. At the same time, data is alternately clocked from the first memory register into a first system register, and from the second memory register into a second system register using a slower-speed system clock. These data transfers are coordinated so that data transfers from the synchronous random access memory into the memory registers do not interfere with data transfers from the memory registers into the system registers. More specifically, the method ensures that the first memory register is loaded from the synchronous random access memory while the data is being transferred from the second memory register into the second system register. On alternate cycles the method ensures that the second memory register is loaded from the synchronous random access memory while data is being transferred from the first memory register into the first system register. In a variation on this embodiment, the first and second memory registers are composed of a plurality of separately-clocked data words.
REFERENCES:
patent: 5487092 (1996-01-01), Finney et al.
patent: 5909701 (1999-06-01), Jeddeloh
patent: 5926838 (1999-07-01), Jeddeloh
patent: 6044023 (1999-06-01), Proebsting
Micro)n Technology, Inc.
Park Vaughan & Fleming LLP
Verbrugge Kevin
LandOfFree
Method for receiving data from a storage device does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method for receiving data from a storage device, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method for receiving data from a storage device will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2535600